Scene Text Recognition with Single-Point Decoding Network
This work addresses the problem of redundant computations in scene text recognition for researchers and practitioners, offering an incremental improvement over existing attention-based methods.
The paper tackles the computational inefficiency of attention-based scene text recognition by proposing an attention-free Single-Point Decoding Network (SPDN) that samples one key point per character, which greatly improves decoding efficiency without sacrificing performance, as verified by experiments on public benchmarks.
In recent years, attention-based scene text recognition methods have been very popular and attracted the interest of many researchers. Attention-based methods can adaptively focus attention on a small area or even single point during decoding, in which the attention matrix is nearly one-hot distribution. Furthermore, the whole feature maps will be weighted and summed by all attention matrices during inference, causing huge redundant computations. In this paper, we propose an efficient attention-free Single-Point Decoding Network (dubbed SPDN) for scene text recognition, which can replace the traditional attention-based decoding network. Specifically, we propose Single-Point Sampling Module (SPSM) to efficiently sample one key point on the feature map for decoding one character. In this way, our method can not only precisely locate the key point of each character but also remove redundant computations. Based on SPSM, we design an efficient and novel single-point decoding network to replace the attention-based decoding network. Extensive experiments on publicly available benchmarks verify that our SPDN can greatly improve decoding efficiency without sacrificing performance.